CN105678316A - Active driving method based on multi-information fusion - Google Patents
Active driving method based on multi-information fusion Download PDFInfo
- Publication number
- CN105678316A CN105678316A CN201511008402.7A CN201511008402A CN105678316A CN 105678316 A CN105678316 A CN 105678316A CN 201511008402 A CN201511008402 A CN 201511008402A CN 105678316 A CN105678316 A CN 105678316A
- Authority
- CN
- China
- Prior art keywords
- traffic
- pedestrian
- vehicle body
- driving
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides an active driving method based on multi-information fusion. In the driving process of a vehicle, a vision sensor is used for detecting a pedestrian in the surrounding environment, and also used for detecting traffic signal lamps, surrounding vehicles and the like; when the pedestrian is detected, whether the pedestrian is a traffic control personnel is judged, if so, actions of the traffic control personnel are recognized; the vision sensor is used for detecting ground traffic signs, acquiring a sign indicating strategy and sending the sign indicating strategy to a driving control module; a vehicle-mounted radar system and the vehicle-mounted vision sensor are used for detecting vehicles in front and at both sides as well as behaviors of the vehicles, judging the judgment on a current road condition of the surrounding vehicles according to their behaviors, and sending driving states of the surrounding vehicles to the driving control module. The active driving method based on multi-information fusion considers relatively fixed detection target information of the traffic lamps and road surface sign lamps, and considers external dynamic information of traffic police command actions, behavior states of the surrounding vehicles and the like, so that active driving has higher flexibility and higher adaptability to the environment.
Description
Technical field
The invention belongs to actively driving technology field, specifically a kind of active drive manner based on Multi-information acquisition.
Background technology
At present actively drives correlation technique from the auxiliary driving field of automobile to automobile, substantially all adopt and traffic information is identified, the information such as including traffic light, zebra crossing, stop line, judge whether to need deceleration, stopping etc. operating. And often there is certain error in the detection and identification for these basic traffic informations, because actively driving vehicle also in test and exploratory stage, so in order to help Driving control decision-making better, it is desirable to provide more abundant information reliable and with a high credibility. Especially traffic safety concerns driver itself and other people safety, ambiguous especially must not.
Summary of the invention
The invention provides a kind of active drive manner based on Multi-information acquisition, the method is based on traffic police's gesture motion identification, traffic light identification, surrounding vehicles Activity recognition, traffic above-ground mark include stop line, zebra crossing, turn marking etc. and identify and the Multi-information acquisition such as other obstacle recognitions, jointly helps control decision module to carry out actively driving.
For achieving the above object, the technical scheme is that, based on the active drive manner of Multi-information acquisition, through the following steps that realize:
S1: in automobile traveling process, detects the pedestrian in surrounding with vision sensor, traffic light and surrounding vehicles etc. is detected simultaneously;
S2: in time pedestrian being detected, to whether pedestrian is that traffic control personnel judge, if traffic control personnel, its action is identified, judges how current this is driven and corresponding driving strategy is sent to Driving control module according to traffic control personnel's action;
S3: vision sensor, to ground road traffic sign detection, obtains mark instruction strategy and is sent to Driving control module; Traffic light are detected by vision sensor, obtain signal lights instruction strategy and are sent to Driving control module;
S4: Vehicular radar system and vehicle-mounted vision sensor detect front and both sides vehicle and driving behavior thereof jointly, judge the surrounding vehicles judgement to current road conditions by its driving behavior, and surrounding vehicles driving states is sent to Driving control module;
S5: obtaining the traffic control corresponding driving strategy of personnel's action, after the behavior state of driving strategy that pavement marker provides, strategy that traffic light provide, surrounding vehicles, the information of each module is weighted merging by Driving control module.
Further, described traffic above-ground mark, including stop line, zebra crossing, turn marking etc.
Further, step S2 judging, whether pedestrian is that traffic control personnel are undertaken by following concrete steps:
Step 1: collect fluorescence waistcoat image pattern and its negative sample of a large amount of pedestrian and traffic control personnel;
Step 2: carry out characteristic statistics by adboost, off-line training obtains the grader of the grader about pedestrian detection and the detection of fluorescence waistcoat, and sets up the color histogram template of fluorescence waistcoat;
Step 3: when active control loop by pedestrian detection module be tested with pedestrian target occur time, to the torso portion of pedestrian, respectively deviation 1/2 is interval up and down, carries out the color histogram template matching of fluorescence waistcoat;
Step 4: measuring similarity reaches after template matching multiple candidate regions of more than 85% and carries out fluorescence waistcoat grader and accurately detect, chooses region that wherein confidence level the is the highest confidence level as final result;
Step 5: when the confidence level of final result is more than threshold value, detects that pedestrian is traffic control personnel.
Further, when detecting that pedestrian is traffic control personnel, the medicated cap of traffic control personnel being carried out type identification, its step is as follows:
A, carried out characteristic statistics by adboost, the alert cap picture of the traffic police of off-line training large sample, and then determine the alert cap grader of traffic police;
B, on the above-mentioned basis detecting traffic control personnel, by the pedestrian head region detected being carried out the expansion in each 1/2 region up and down;
C, then the head zone after expanding is carried out the detection of the alert cap of traffic police, utilize and step A trains the alert cap grader of the traffic police obtained, it is judged that whether having the alert cap of traffic police in this region, if had, this traffic control personnel are traffic police; Otherwise for association's duty.
Further, in step S3, the detection method to traffic light, realize particular by following steps:
D1: utilize vehicle GPS that vehicle body position is positioned, to obtain vehicle body positional information;
D2: utilize vehicle body place lane information, searches the mode of comparison by map and the GPS result positioned carries out first time correction;
D3: utilize Vehicular radar system that vehicle body position is carried out second-order correction;
D4: after getting the exact position that vehicle body is real-time, controls module and precise position information is passed to mapping module, the distance of inquiry current location distance junction ahead, according to the distance of junction ahead and self speed, calculate the time arriving junction ahead;
D5: in the world coordinate system centered by vehicle body, obtains the coordinate of signal lights, is converted to image coordinate system by world coordinate system, it is determined that the image coordinate region of signal lights;
D6: signal lights is detected in the image coordinate region of lock semaphore in image coordinate system.
As further, in step D2, vehicle body place lane information is obtained by following method: while GPS obtains vehicle body positional information, vehicle-mounted vision sensor checks the lane line on road surface, and by lane line coordinate position relation in visual scene, it is determined that the track at vehicle body place.
As further, in step D3, second-order correction is: Vehicular radar system detection road border projection on both sides of the road, by the width on partial 3 d information reconstruction commercial measurement road border, and determines the accurate distance on vehicle body distance road border, both sides.
As further, after obtaining vehicle body distance signal lamp distance d in step s 4, according to the difference H-h of bodywork height Yu signal lights height two right-angle sides obtaining triangle, obtaining the length on Article 3 limit, and then set up world coordinate system centered by vehicle body.
As further, vehicle behavior in step s 4, including accelerating, slow down, brake the actions such as stopping.
As further, Weighted Fusion refers to when the driving strategy having traffic police to command in step s 5, is as the criterion with traffic police commander; When not having traffic police to command, the strategy combination that the strategy that traffic light are provided and traffic above-ground mark provide, and take into account surrounding vehicles driving behavior, driving behavior generally remains consistent with surrounding vehicles.
Due to the fact that the above technical scheme of employing, following technique effect can be obtained: the active driving technology of the present invention not only considers traffic lights and compares the detection target information fixed with pavement marker lamp, also contemplate traffic police and command the extraneous multidate informations such as the action behavior state with surrounding vehicles, make actively to drive that there is greater flexibility and the adaptive capacity that environment is higher. Utilizing the behavior state of most vehicle around, keeping self transport condition to coordinate mutually with surrounding majority vehicle, thus ensure that the safety actively driving vehicle to a certain extent.
Utilizing and be accurately positioned the body of a motor car of acquisition and the real-time range information of signal lights, the prior information such as binding signal lamp height, bodywork height, in conjunction with geometrical relationship, it is determined that signal lights position range in world coordinate system. Utilize world coordinates to be tied to the conversion of image coordinate system, obtain the position range in image coordinate system and then the scope of minimizing cycling among windows, drastically increase the efficiency of searching and detecting such that it is able to the information giving system prompt traffic light earlier.
Utilize the distribution of color rectangular histogram of the fluorescence waistcoat of traffic control personnel, close in the pedestrian's torso portion detected and in scope, carry out Preliminary detection, then the candidate region detected is carried out the accurate identification of grader, thus improve the recognition efficiency of traffic control personnel. By the alert cap of traffic police is set up grader, when detecting traffic control personnel, in its head zone neighborhood, carry out the alert cap detection of traffic police, thus differentiating whether this traffic control personnel are traffic police.
Accompanying drawing explanation
The present invention has accompanying drawing 6 width:
Fig. 1 is the active drive manner FB(flow block) based on Multi-information acquisition;
Fig. 2 is traffic control personal identification process flow block diagram;
Fig. 3 identifies process flow block diagram for traffic police;
Fig. 4 is traffic light testing process block diagrams;
Fig. 5 is vehicle body and signal lights distance and position relation schematic diagram;
Fig. 6 is the expansion schematic diagram of target area in image coordinate system in embodiment 3.
Detailed description of the invention
By the examples below, and in conjunction with accompanying drawing, technical scheme is described in further detail.
Embodiment 1
Active drive manner based on Multi-information acquisition, it is characterised in that through the following steps that realize:
S1: in automobile traveling process, detects the pedestrian in surrounding with vision sensor, traffic light and surrounding vehicles is detected simultaneously;
S2: in time pedestrian being detected, to whether pedestrian is that traffic control personnel judge, if traffic control personnel, its action is identified, judges how current this is driven and corresponding driving strategy is sent to Driving control module according to traffic control personnel's action; Be used herein as HMM and detect traffic police's action in conjunction with viterbi algorithm, it is possible to use additive method, according to traffic police's action judge current this how to drive stopping, slow down still normal through etc.
S3: vision sensor, to ground road traffic sign detection, obtains mark instruction strategy and is sent to Driving control module; Traffic light are detected by vision sensor, obtain signal lights instruction strategy and are sent to Driving control module; Described traffic above-ground mark, including stop line, zebra crossing, turn marking etc.;
S4: Vehicular radar system and vehicle-mounted vision sensor detect front and both sides vehicle and driving behavior thereof jointly, the surrounding vehicles judgement to current road conditions is judged by its driving behavior, such as when surrounding vehicles all reduces speed now, can tentatively infer front be likely to have need slow down factor (such as, having traffic police to command by red light or front needs deceleration to detour), and surrounding vehicles driving states is sent to Driving control module, do so is based on the action of most vehicles around; Its driving behavior includes the actions such as acceleration, deceleration, brake stopping.
S5: after the driving behavior state indicating strategy, surrounding vehicles that, traffic light tactful in the instruction obtaining the traffic control corresponding driving strategy of personnel's action, pavement marker provides provide, the information of each module is weighted merging by Driving control module. Weighted Fusion refers to when the driving strategy having traffic police to command, and is as the criterion with traffic police commander; When not having traffic police to command, the strategy combination that the strategy that traffic light are provided and traffic above-ground mark provide, and take into account surrounding vehicles driving behavior, driving behavior generally remains consistent with surrounding vehicles.
The traffic lights that considers that the present invention proposes compares the detection target information fixed with pavement marker lamp, also contemplating traffic police and command the extraneous multidate informations such as the action behavior state with surrounding vehicles, what multiple channel obtained drives, to active, the method having the information of reference value to merge. According to detecting surrounding vehicles and calculating its running status, many-sided consideration traffic lights and the information such as pavement marker and commander traffic police on driving strategy, and maintenance is consistent with surrounding vehicles as far as possible.
Embodiment 2
This embodiment as different from Example 1 in step s3, the detection method to traffic light, particular by following steps realize:
It is applied in the method identifying traffic control personnel in active driving technology, through the following steps that realize:
Step 1: collect fluorescence waistcoat image pattern and its negative sample of a large amount of pedestrian and traffic control personnel;
Step 2: carry out characteristic statistics by adboost, off-line training obtains the grader of the grader about pedestrian detection and the detection of fluorescence waistcoat, and is obtained the color histogram template of fluorescence waistcoat by rbf neural metwork training;
Step 3: when active control loop by pedestrian detection module be tested with pedestrian target occur time, to the torso portion of pedestrian, respectively deviation 1/2 is interval up and down, carries out the color histogram template matching of fluorescence waistcoat;
Step 4: measuring similarity reaches after template matching multiple candidate regions of more than 85% and carries out fluorescence waistcoat grader and accurately detect, chooses region that wherein confidence level the is the highest confidence level as final result;
Step 5: when the confidence level of final result is more than threshold value 95%, detects that pedestrian is that human pilot is pointed out the step switching to manual drive pattern or carries out other work by traffic control personnel.
When detecting that pedestrian is traffic control personnel, the medicated cap of traffic control personnel being carried out type identification, its step is as follows: carry out characteristic statistics by adboost, the alert cap picture of the traffic police of off-line training large sample, and then determines the alert cap grader of traffic police; On the above-mentioned basis detecting traffic control personnel, by the pedestrian head region detected being carried out the expansion in each 1/2 region up and down; Then the head zone after expanding is carried out the detection of the alert cap of traffic police, utilizes and step A trains the alert cap grader of the traffic police obtained, it is judged that whether having the alert cap of traffic police in this region, if had, this traffic control personnel are traffic police; Otherwise for association's duty.
Utilize the distribution of color rectangular histogram of the fluorescence waistcoat of traffic control personnel, close in the pedestrian's torso portion detected and in scope, carry out Preliminary detection, then the candidate region detected is carried out the accurate identification of grader, thus improve the recognition efficiency of traffic control personnel. Pedestrian detection is combined by the present invention with the alert cap detection of traffic police, thus when detecting traffic control personnel, carrying out the alert cap detection of traffic police, thus differentiating whether this traffic control personnel are traffic police in its head zone neighborhood. Follow-up the method can also be used to carry out classifying to other kinds of traffic control personnel or other staff and identify.
Embodiment 3
This embodiment and embodiment 1 and 2, the difference is that, detection method to traffic light in step S3, realize particular by following steps:
D1: utilize vehicle GPS that vehicle body position carries out " slightly " location, to obtain vehicle body positional information; Often there is certain error in the position this time obtained, maximum possible has several meters; It is therefore desirable to utilize the correction of following twice.
D2: while GPS obtains vehicle body positional information, vehicle-mounted vision sensor checks the lane line on road surface, and by lane line coordinate position relation in visual scene, it is determined that the track at vehicle body place; Utilize vehicle body place lane information, search the mode of comparison by map and the GPS result positioned is carried out first time correction;
D3: Vehicular radar system detection road border projection on both sides of the road is commonly called as " road serrated edge ", by the width on partial 3 d information reconstruction commercial measurement road border, and determines the accurate distance on vehicle body distance road border, both sides; Utilize road width and vehicle body distance road both sides frontier distance, it is possible to vehicle body position is carried out second-order correction. In this manner it is possible to obtain the vehicle body positional information that precision is relatively significantly high, specifically as shown in Figure 1.
D4: after getting the exact position that vehicle body is real-time, control module and precise position information is passed to mapping module, the distance of inquiry current location distance junction ahead, distance according to junction ahead and self speed, calculate the time arriving junction ahead, in order to when arriving junction ahead, corresponding decision made by vehicle; After obtaining vehicle body distance signal lamp distance d, according to the difference H-h of bodywork height Yu signal lights height two right-angle sides obtaining triangle, obtain the length on Article 3 limit, and then centered by vehicle body, set up world coordinate system;
D5: in the world coordinate system centered by vehicle body, obtains the coordinate of signal lights, is converted to image coordinate system by world coordinate system, it is determined that the image coordinate region of signal lights;
D6: signal lights is detected in the image coordinate region of lock semaphore in image coordinate system, in order to better fault-tolerant, has carried out the expansion of each 1 or 2 times up and down to object detection area, in order to avoid measurement error causes the missing inspection of traffic light. As shown in Figure 6: the coordinate of A, B, C is borderline region, ROI is the image coordinate region of signal lights, and ROI ' is the image coordinate region of the signal lights after expanding.
As shown in Figure 6, it is the detection carrying out signal lights in ROI ' region, this avoid the huge calculation cost of entire image search, also make the physical location of vision-based detection signal lights become more accurate simultaneously. Above-mentioned GPS location, vehicle-mounted vision sensor detection lane line and laser radar detection road border, three is executed in parallel.
After the method that vehicle body exact position is measured by the present invention: GPS obtains vehicle body approximate location, utilizing vision sensor detection lane line thus confirming track, vehicle body place, position is corrected by inquiry cartographic information; Utilize laser radar sensor detection road border simultaneously, adopt the mode that partial 3 d is rebuild to get vehicle body distance both sides frontier distance, and then vehicle body position is carried out secondary correction.
The above; it is only the present invention preferably detailed description of the invention; but protection scope of the present invention is not limited thereto; any those familiar with the art is in the technical scope of present disclosure; it is equal to replacement according to technical scheme and inventive concept thereof or is changed, all should be encompassed within protection scope of the present invention.
Claims (10)
1. based on the active drive manner of Multi-information acquisition, it is characterised in that through the following steps that realize:
S1: in automobile traveling process, detects the pedestrian in surrounding with vision sensor, traffic light and surrounding vehicles is detected simultaneously;
S2: in time pedestrian being detected, to whether pedestrian is that traffic control personnel judge, if traffic control personnel, its action is identified, judges how current this is driven and corresponding driving strategy is sent to Driving control module according to traffic control personnel's action;
S3: vision sensor, to ground road traffic sign detection, obtains mark instruction strategy and is sent to Driving control module; Traffic light are detected by vision sensor, obtain signal lights instruction strategy and are sent to Driving control module;
S4: Vehicular radar system and vehicle-mounted vision sensor detect front and both sides vehicle and driving behavior thereof jointly, judge the surrounding vehicles judgement to current road conditions by its driving behavior, and surrounding vehicles driving states is sent to Driving control module;
S5: after the driving behavior state indicating strategy, surrounding vehicles that, traffic light tactful in the instruction obtaining the traffic control corresponding driving strategy of personnel's action, pavement marker provides provide, the information of each module is weighted merging by Driving control module.
2. the active drive manner based on Multi-information acquisition according to claim 1, it is characterised in that judge in step S2 whether pedestrian is that traffic control personnel are undertaken by following concrete steps:
Step 1: collect fluorescence waistcoat image pattern and its negative sample of a large amount of pedestrian and traffic control personnel;
Step 2: carry out characteristic statistics by adboost, off-line training obtains the grader of the grader about pedestrian detection and the detection of fluorescence waistcoat, and sets up the color histogram template of fluorescence waistcoat;
Step 3: when active control loop by pedestrian detection module be tested with pedestrian target occur time, to the torso portion of pedestrian, respectively deviation 1/2 is interval up and down, carries out the color histogram template matching of fluorescence waistcoat;
Step 4: measuring similarity reaches after template matching multiple candidate regions of more than 85% and carries out fluorescence waistcoat grader and accurately detect, chooses region that wherein confidence level the is the highest confidence level as final result;
Step 5: when the confidence level of final result is more than threshold value, detects that pedestrian is traffic control personnel.
3. the active drive manner based on Multi-information acquisition according to claim 2, it is characterised in that when detecting that pedestrian is traffic control personnel, the medicated cap of traffic control personnel being carried out type identification, its step is as follows:
A, carried out characteristic statistics by adboost, the alert cap picture of the traffic police of off-line training large sample, and then determine the alert cap grader of traffic police;
B, on the above-mentioned basis detecting traffic control personnel, by the pedestrian head region detected being carried out the expansion in each 1/2 region up and down;
C, then the head zone after expanding is carried out the detection of the alert cap of traffic police, utilize and step A trains the alert cap grader of the traffic police obtained, it is judged that whether having the alert cap of traffic police in this region, if had, this traffic control personnel are traffic police; Otherwise for association's duty.
4. the active drive manner based on Multi-information acquisition according to claim 3, it is characterised in that adopt HMM to detect traffic police's action in conjunction with viterbi algorithm in step S2.
5. the active drive manner based on Multi-information acquisition according to claim 1, it is characterised in that in step S3, the detection method to traffic light, realize particular by following steps:
D1: utilize vehicle GPS that vehicle body position is positioned, to obtain vehicle body positional information;
D2: utilize vehicle body place lane information, searches the mode of comparison by map and the GPS result positioned carries out first time correction;
D3: utilize Vehicular radar system that vehicle body position is carried out second-order correction;
D4: after getting the exact position that vehicle body is real-time, controls module and precise position information is passed to mapping module, the distance of inquiry current location distance junction ahead, according to the distance of junction ahead and self speed, calculate the time arriving junction ahead;
D5: in the world coordinate system centered by vehicle body, obtains the coordinate of signal lights, is converted to image coordinate system by world coordinate system, it is determined that the image coordinate region of signal lights;
D6: signal lights is detected in the image coordinate region of lock semaphore in image coordinate system.
6. the active drive manner based on Multi-information acquisition according to claim 5, it is characterized in that, in step D2, vehicle body place lane information is obtained by following method: while GPS obtains vehicle body positional information, vehicle-mounted vision sensor checks the lane line on road surface, and by lane line coordinate position relation in visual scene, it is determined that the track at vehicle body place.
7. the active drive manner based on Multi-information acquisition according to claim 5, it is characterized in that, in step D3, second-order correction is: Vehicular radar system detection road border projection on both sides of the road, by the width on partial 3 d information reconstruction commercial measurement road border, and determine the accurate distance on vehicle body distance road border, both sides.
8. the active drive manner based on Multi-information acquisition according to any one of claim 5-7, it is characterized in that, after obtaining vehicle body distance signal lamp distance d in step s 4, difference H-h according to bodywork height Yu signal lights height obtains two right-angle sides of triangle, obtain the length on Article 3 limit, and then centered by vehicle body, set up world coordinate system.
9. the active drive manner based on Multi-information acquisition according to claim 1, it is characterised in that vehicle drive behavior in step s 4, including accelerating, slow down, brake stopping action.
10. the active drive manner based on Multi-information acquisition according to claim 9, it is characterised in that Weighted Fusion refers to when the driving strategy having traffic police to command in step s 5, is as the criterion with traffic police commander; When not having traffic police to command, the strategy combination that the strategy that traffic light are provided and traffic above-ground mark provide, and take into account surrounding vehicles driving behavior, driving behavior generally remains consistent with surrounding vehicles.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511008402.7A CN105678316B (en) | 2015-12-29 | 2015-12-29 | Active drive manner based on multi-information fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201511008402.7A CN105678316B (en) | 2015-12-29 | 2015-12-29 | Active drive manner based on multi-information fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105678316A true CN105678316A (en) | 2016-06-15 |
CN105678316B CN105678316B (en) | 2019-08-27 |
Family
ID=56189684
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201511008402.7A Active CN105678316B (en) | 2015-12-29 | 2015-12-29 | Active drive manner based on multi-information fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105678316B (en) |
Cited By (24)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106128115A (en) * | 2016-08-01 | 2016-11-16 | 青岛理工大学 | Fusion method for detecting road traffic information based on double cameras |
CN107490382A (en) * | 2017-07-31 | 2017-12-19 | 中北智杰科技(北京)有限公司 | A kind of pilotless automobile path planning system and control method |
CN108107459A (en) * | 2017-12-11 | 2018-06-01 | 浙江捷尚人工智能研究发展有限公司 | Robot orientation detecting method, apparatus and system based on navigation system |
CN108458745A (en) * | 2017-12-23 | 2018-08-28 | 天津国科嘉业医疗科技发展有限公司 | A kind of environment perception method based on intelligent detection equipment |
CN108482246A (en) * | 2018-02-08 | 2018-09-04 | 深圳市赛格导航科技股份有限公司 | A kind of vehicle carried driving householder method, device, equipment and storage medium |
CN109427199A (en) * | 2017-08-24 | 2019-03-05 | 北京三星通信技术研究有限公司 | For assisting the method and device of the augmented reality driven |
CN109455178A (en) * | 2018-11-13 | 2019-03-12 | 吉林大学 | A kind of road vehicles traveling active control system and method based on binocular vision |
CN109478336A (en) * | 2016-07-21 | 2019-03-15 | 五十铃自动车株式会社 | Image processing apparatus and image processing method |
CN109712431A (en) * | 2017-10-26 | 2019-05-03 | 丰田自动车株式会社 | Drive assistance device and driving assistance system |
CN109828571A (en) * | 2019-02-18 | 2019-05-31 | 奇瑞汽车股份有限公司 | Automatic driving vehicle, method and apparatus based on V2X |
CN110335484A (en) * | 2019-08-08 | 2019-10-15 | 北京小马智行科技有限公司 | Control the method and device of vehicle driving |
CN110427823A (en) * | 2019-06-28 | 2019-11-08 | 北京大学 | Joint objective detection method and device based on video frame and pulse array signals |
CN110542931A (en) * | 2018-05-28 | 2019-12-06 | 北京京东尚科信息技术有限公司 | traffic light detection method and device, electronic equipment and computer readable medium |
CN110636964A (en) * | 2017-05-23 | 2019-12-31 | 奥迪股份公司 | Method for determining a driving instruction |
CN110659543A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Vehicle control method and system based on gesture recognition and vehicle |
CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, device, system, storage medium and processor |
WO2020146983A1 (en) * | 2019-01-14 | 2020-07-23 | 深圳市大疆创新科技有限公司 | Lane detection method and apparatus, lane detection device, and mobile platform |
CN111507204A (en) * | 2020-03-27 | 2020-08-07 | 北京百度网讯科技有限公司 | Method and device for detecting countdown signal lamp, electronic equipment and storage medium |
CN111564051A (en) * | 2020-04-28 | 2020-08-21 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
CN111634290A (en) * | 2020-05-22 | 2020-09-08 | 华域汽车系统股份有限公司 | Advanced driving assistance forward fusion system and method |
CN112088371A (en) * | 2018-05-04 | 2020-12-15 | 高通股份有限公司 | System and method for capturing and distributing information collected from signs |
CN113140120A (en) * | 2020-01-16 | 2021-07-20 | 华为技术有限公司 | Method and device for determining traffic indication information |
CN113784482A (en) * | 2021-09-18 | 2021-12-10 | 合肥工业大学 | Intelligent headlamp system of vehicle |
CN114527735A (en) * | 2020-10-30 | 2022-05-24 | 奥迪股份公司 | Method and device for controlling an autonomous vehicle, vehicle and storage medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101357616A (en) * | 2008-09-27 | 2009-02-04 | 清华大学 | Intelligent environment-friendly type vehicle structure |
CN202424782U (en) * | 2012-01-06 | 2012-09-05 | 中科院微电子研究所昆山分所 | Vehicle-mounted terminal device |
CN104134349A (en) * | 2014-08-07 | 2014-11-05 | 北京航空航天大学 | Bus road condition processing system and method based on traffic multi-source data fusion |
CN104392625A (en) * | 2014-11-26 | 2015-03-04 | 浙江大学 | Vehicle automatic pilot system and method based on various sensors |
CN104477167A (en) * | 2014-11-26 | 2015-04-01 | 浙江大学 | Intelligent driving system and control method thereof |
CN104656651A (en) * | 2013-11-21 | 2015-05-27 | 现代摩比斯株式会社 | Apparatus And Method For Controlling Automatic Driving Of Vehicle Based On Sensor Fusion |
-
2015
- 2015-12-29 CN CN201511008402.7A patent/CN105678316B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101357616A (en) * | 2008-09-27 | 2009-02-04 | 清华大学 | Intelligent environment-friendly type vehicle structure |
CN202424782U (en) * | 2012-01-06 | 2012-09-05 | 中科院微电子研究所昆山分所 | Vehicle-mounted terminal device |
CN104656651A (en) * | 2013-11-21 | 2015-05-27 | 现代摩比斯株式会社 | Apparatus And Method For Controlling Automatic Driving Of Vehicle Based On Sensor Fusion |
CN104134349A (en) * | 2014-08-07 | 2014-11-05 | 北京航空航天大学 | Bus road condition processing system and method based on traffic multi-source data fusion |
CN104392625A (en) * | 2014-11-26 | 2015-03-04 | 浙江大学 | Vehicle automatic pilot system and method based on various sensors |
CN104477167A (en) * | 2014-11-26 | 2015-04-01 | 浙江大学 | Intelligent driving system and control method thereof |
Cited By (32)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109478336B (en) * | 2016-07-21 | 2022-05-10 | 五十铃自动车株式会社 | Image processing apparatus and image processing method |
CN109478336A (en) * | 2016-07-21 | 2019-03-15 | 五十铃自动车株式会社 | Image processing apparatus and image processing method |
CN106128115A (en) * | 2016-08-01 | 2016-11-16 | 青岛理工大学 | Fusion method for detecting road traffic information based on double cameras |
CN106128115B (en) * | 2016-08-01 | 2018-11-30 | 青岛理工大学 | Fusion method for detecting road traffic information based on double cameras |
CN110636964A (en) * | 2017-05-23 | 2019-12-31 | 奥迪股份公司 | Method for determining a driving instruction |
CN107490382A (en) * | 2017-07-31 | 2017-12-19 | 中北智杰科技(北京)有限公司 | A kind of pilotless automobile path planning system and control method |
CN109427199A (en) * | 2017-08-24 | 2019-03-05 | 北京三星通信技术研究有限公司 | For assisting the method and device of the augmented reality driven |
CN109712431B (en) * | 2017-10-26 | 2021-03-12 | 丰田自动车株式会社 | Driving support device and driving support system |
CN109712431A (en) * | 2017-10-26 | 2019-05-03 | 丰田自动车株式会社 | Drive assistance device and driving assistance system |
CN108107459A (en) * | 2017-12-11 | 2018-06-01 | 浙江捷尚人工智能研究发展有限公司 | Robot orientation detecting method, apparatus and system based on navigation system |
CN108458745A (en) * | 2017-12-23 | 2018-08-28 | 天津国科嘉业医疗科技发展有限公司 | A kind of environment perception method based on intelligent detection equipment |
CN108482246A (en) * | 2018-02-08 | 2018-09-04 | 深圳市赛格导航科技股份有限公司 | A kind of vehicle carried driving householder method, device, equipment and storage medium |
CN112088371A (en) * | 2018-05-04 | 2020-12-15 | 高通股份有限公司 | System and method for capturing and distributing information collected from signs |
CN110542931B (en) * | 2018-05-28 | 2021-12-28 | 北京京东乾石科技有限公司 | Traffic light detection method and device, electronic equipment and computer readable medium |
CN110542931A (en) * | 2018-05-28 | 2019-12-06 | 北京京东尚科信息技术有限公司 | traffic light detection method and device, electronic equipment and computer readable medium |
CN110659543A (en) * | 2018-06-29 | 2020-01-07 | 比亚迪股份有限公司 | Vehicle control method and system based on gesture recognition and vehicle |
CN109455178B (en) * | 2018-11-13 | 2023-11-17 | 吉林大学 | Road traffic vehicle driving active control system and method based on binocular vision |
CN109455178A (en) * | 2018-11-13 | 2019-03-12 | 吉林大学 | A kind of road vehicles traveling active control system and method based on binocular vision |
WO2020146983A1 (en) * | 2019-01-14 | 2020-07-23 | 深圳市大疆创新科技有限公司 | Lane detection method and apparatus, lane detection device, and mobile platform |
CN109828571A (en) * | 2019-02-18 | 2019-05-31 | 奇瑞汽车股份有限公司 | Automatic driving vehicle, method and apparatus based on V2X |
CN110427823A (en) * | 2019-06-28 | 2019-11-08 | 北京大学 | Joint objective detection method and device based on video frame and pulse array signals |
CN110335484A (en) * | 2019-08-08 | 2019-10-15 | 北京小马智行科技有限公司 | Control the method and device of vehicle driving |
WO2021143611A1 (en) * | 2020-01-16 | 2021-07-22 | 华为技术有限公司 | Method and device for determining traffic indication information |
CN113140120A (en) * | 2020-01-16 | 2021-07-20 | 华为技术有限公司 | Method and device for determining traffic indication information |
CN111289003A (en) * | 2020-02-06 | 2020-06-16 | 广州小马智行科技有限公司 | Path planning method, device, system, storage medium and processor |
CN111507204A (en) * | 2020-03-27 | 2020-08-07 | 北京百度网讯科技有限公司 | Method and device for detecting countdown signal lamp, electronic equipment and storage medium |
CN111564051B (en) * | 2020-04-28 | 2021-07-20 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
CN111564051A (en) * | 2020-04-28 | 2020-08-21 | 安徽江淮汽车集团股份有限公司 | Safe driving control method, device and equipment for automatic driving automobile and storage medium |
CN111634290A (en) * | 2020-05-22 | 2020-09-08 | 华域汽车系统股份有限公司 | Advanced driving assistance forward fusion system and method |
CN111634290B (en) * | 2020-05-22 | 2023-08-11 | 华域汽车系统股份有限公司 | Advanced driving assistance forward fusion system and method |
CN114527735A (en) * | 2020-10-30 | 2022-05-24 | 奥迪股份公司 | Method and device for controlling an autonomous vehicle, vehicle and storage medium |
CN113784482A (en) * | 2021-09-18 | 2021-12-10 | 合肥工业大学 | Intelligent headlamp system of vehicle |
Also Published As
Publication number | Publication date |
---|---|
CN105678316B (en) | 2019-08-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105678316A (en) | Active driving method based on multi-information fusion | |
CN105489035B (en) | Apply the method that traffic lights are detected in active driving technology | |
US11436919B2 (en) | Method and apparatus for determining driving strategy of a vehicle | |
US10239539B2 (en) | Vehicle travel control method and vehicle travel control device | |
US10730503B2 (en) | Drive control system | |
JP7119365B2 (en) | Driving behavior data generator, driving behavior database | |
US20140236463A1 (en) | Enhanced clear path detection in the presence of traffic infrastructure indicator | |
CN108445885A (en) | A kind of automated driving system and its control method based on pure electric vehicle logistic car | |
US11216689B2 (en) | Detection of emergency vehicles | |
CN106225789A (en) | A kind of onboard navigation system with high security and bootstrap technique thereof | |
CN105892464A (en) | Special car automatic driving system based on fixed routes and driving method for same | |
US20120327188A1 (en) | Vehicle-Mounted Environment Recognition Apparatus and Vehicle-Mounted Environment Recognition System | |
CN107992829A (en) | A kind of traffic lights track level control planning extracting method and device | |
CN113247014B (en) | Confidence identification method and system for automatic driving system | |
CN109632333A (en) | Automatic driving vehicle performance test methods, device, equipment and readable storage medium storing program for executing | |
JP3857698B2 (en) | Driving environment recognition device | |
CN110562269A (en) | Method for processing fault of intelligent driving vehicle, vehicle-mounted equipment and storage medium | |
US20230242149A1 (en) | Radar object classification based on radar cross-section data | |
CN110304055A (en) | A kind of car actively alleviates the control system and its application method of pedestrian impact | |
CN108407806A (en) | Auxiliary driving method and device | |
US20230027357A1 (en) | Vehicle control system, vehicle control method, and storage medium | |
JP2021082286A (en) | System and method for improving lane change detection, and non-temporary computer-readable medium | |
KR20190064228A (en) | Apparatus and method of providing information of traffic lanes using image sensing and vehicle control method using the same | |
US9376052B2 (en) | Method for estimating a roadway course and method for controlling a light emission of at least one headlight of a vehicle | |
US20240208547A1 (en) | Route planning system and method of self-driving vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |